Autonomous Intelligent Workflow Communications Agent

Modern industries increasingly rely on automated systems to manage complex workflows, communications, and task execution across fields as varied as system design and development, finance, and project management. As the scale of projects and operational complexity grows, particularly in fields involving large-scale hardware and software design, the demand for human resources to manage communications, monitor tasks, and execute predefined workflows has become a significant challenge.

Engineers and other professionals are often tasked with overseeing highly intricate workflows involving numerous steps, each of which requires monitoring and execution. Such workflows typically involve various types of communication, including the processing of task-related instructions, status updates, and error reports. Human operators must not only interpret these communications but also manually initiate responses, trigger execution of scripts (predefined instructions and/or sets of instructions), or troubleshoot errors, leading to delays, inefficiencies, and increased resource consumption.

Furthermore, as systems become more sophisticated, they may produce an overwhelming amount of data and communications that require processing. This growing complexity exacerbates the strain on human resources, often requiring teams to rely on manual effort for repetitive and routine tasks, such as parsing messages or initiating workflow steps based on predefined instructions.

Existing automation tools and systems provide limited solutions to this problem, often focusing on specific workflows or tasks without offering the flexibility needed to adapt to dynamic communication environments or handle a wide range of inputs. Moreover, current solutions may lack the ability to intelligently interpret complex, non-standardized instructions, leading to bottlenecks in task execution and mismanagement of workflow priorities.

As pressure to reduce human involvement in routine operations increases, there is a growing need for a more sophisticated and intelligent system capable of autonomously managing communication workflows, processing a variety of inputs, and efficiently executing tasks across multiple domains without extensive human oversight.

As used herein, a domain refers to a distinct area of operation or specialization within which specific tasks, processes, or workflows are performed. Domains may encompass various fields such as physical electronics and/or semiconductor design, project management, finance, human resources management, or other fields requiring structured communication and task management. Each domain is characterized by its own set of requirements, workflows, and communication protocols, which may be tailored to meet the operational needs of a particular industry or application. A domain may include both technical and non-technical fields where automation can enhance efficiency by managing communication-driven workflows. For example, in physical design engineering, a domain might encompass tasks such as timing analysis, congestion analysis, or routing.

Embodiments of techniques described herein provide systems and methods for autonomously managing communication workflows and executing tasks across multiple domains, significantly reducing the need for manual human intervention by leveraging intelligent automation to process both predefined and dynamically generated instructions. By integrating communication parsing, task orchestration, and workflow execution capabilities, such embodiments facilitate more efficient handling of routine operations while allowing human resources to focus on complex, high-level tasks. The described techniques are adaptable to different environments, supporting various communication interfaces and enabling integration with existing infrastructure, thereby offering improved flexibility, scalability, and operational efficiency.

As used herein, a workflow communications agent (WCA) is an executable component configured to manage, interpret, and execute task-related communications between human users and/or other WCAs within a networked environment. Each WCA automates the handling of messages containing instructions, using both predefined instruction sets and dynamically generated instructions to process and respond to tasks. In certain embodiments, a WCA utilizes one or more large language models (LLMs) to interpret unstructured or ambiguous content, identifying relevant instructions even in non-standardized messages. In some embodiments, WCAs coordinate task execution across multiple agents and communicate status updates, results, or additional instructions as needed. In various embodiments, each WCA operates across one or more processors, potentially in multi-operating system environments, and may interact with other system components such as memory, processors, and specific tools or applications to fulfill its assigned tasks.

1 FIG. 100 110 150 illustrates a communication workflowbetween multiple workflow communications agents and/or their corresponding human users in a manner facilitating managed workflow communications, in accordance with some embodiments. The system includes two distinct domains, indicated generally atand, each representing a separate area of operation. Each domain includes two workflow communications agents that coordinate communications between human users and external systems.

110 130 135 120 150 170 175 160 Within domain, two workflow communications agents identified as AgentAand AgentBare configured to manage communications and tasks on behalf of a user Hal. Similarly, in domain, two workflow communications agents identified as AgentAand AgentBhandle communications and tasks on behalf of another user Robbie. The workflow communications agents in each domain autonomously manage predefined workflows, leveraging communication parsing and task execution functionalities to ensure coordination between human users and their associated tasks.

120 110 122 160 150 162 120 130 135 160 170 175 In the depicted embodiment, user Halis linked to the workflow communications agents in domainvia a first message address(“Hal@chip.com”), while Robbieis connected to the agents in domainvia a second message address(“Robbie@chip.com”). These message addresses serve as communication interfaces through which the workflow communications agents receive and process incoming instructions. The workflow communications agents within each domain exchange information with their respective users as well as between themselves, as indicated by the bidirectional arrows between user Hal, AgentA, AgentB, user Robbie, AgentA, and AgentB.

100 120 160 130 135 110 170 175 150 110 150 The illustrated communication workflowfacilitates cross-domain communication, enabling Haland Robbieto share task-related information through their respective agents. For instance, AgentAand AgentBin domaincommunicate with AgentAand AgentBin domainto ensure coordination of tasks that may span across those domains,. This inter-agent communication allows for collaboration between users located in different domains.

130 110 170 150 120 160 135 175 In various embodiments, communication between workflow communications agents is managed autonomously, leveraging parsing and processing capabilities to interpret both predefined and dynamically generated instructions, with each agent capable of handling multiple tasks substantially simultaneously. For example, AgentAin domaincan communicate with AgentAin domain, exchanging workflow information between Haland Robbie. Additionally, AgentBand AgentBensure performance of task execution, such as based on sets of instructions that are predefined (e.g., scripts) and/or dynamically generated via a large language model (LLM) or other natural-language processor.

As used herein, a large language model (LLM) refers to a type of machine learning model that is trained on large amounts of textual data and designed to understand, generate, and interpret human language. LLMs are capable of processing complex, context-sensitive instructions and generating responses or actions based on natural language input. In the context of the techniques described herein, an LLM is used to interpret communications that may contain dynamically generated or non-predefined instructions, allowing the system to autonomously convert human language into structured tasks or workflows. The LLM's flexibility enables it to handle a wide range of inputs, including unstructured or partially structured text, making it ideal for environments where users provide instructions that vary in format or detail.

2 FIG. 200 200 230 235 200 illustrates an embodiment of a workflow communications agent (WCA), which automates communication and task execution across various domains. In this embodiment, the WCAis depicted as operating with bifurcated functionality across a local serverand a remote server. However, in other embodiments, the WCAmay not be bifurcated in this manner and can be implemented on a single server or system.

200 200 200 200 While examples described herein utilize email-based messages for ease of illustration, it will be appreciated that in various embodiments, the workflow communications agentmay coordinate and manage other types of communications in lieu of or in addition to email messages. For example, the WCAmay interact with task management systems via API calls, instant messaging platforms, or integrated project management tools to receive, process, and respond to task-related messages. The WCAmay also utilize various communication protocols (such as RESTful web services, JSON-based data exchanges, or direct database interactions) to facilitate workflow coordination. Furthermore, the WCAmay coordinate, manage, and operate via one or more messaging services (e.g., Slack, Microsoft Teams, SMS, etc.), allowing for greater flexibility in how tasks are communicated and executed across one or more domains.

230 235 230 235 In certain embodiments, each respective server,may implement a different operating system. For example, in certain embodiments the local serveroperates using a first operating system (e.g., Microsoft Windows), while remote serveroperates using a second operating system (e.g., a Linux or other *nix operating system).

280 280 In the depicted embodiment, a human userrepresents an individual who performs various roles within a workflow. This individual may act as a tile lead, a primary engineer for Team 1, or a team member for Team 2. The user can receive communications in any of these capacities, as well as communications directed to the human userin their individual capacity (him/herself), depending on the specific context or job function within the domain. For example, as a tile lead, the user might be responsible for managing tasks related to a specific section of a chip design, while as a primary engineer or team member, they may oversee or contribute to broader project goals.

280 200 234 200 In the depicted embodiment, interactions of/for the human userwith the WCAare typically initiated through email messages, which are processed by the email and application programming interface (API) system. The WCAinterprets these messages in accordance with the destination role and/or context, ensuring that tasks or updates are handled appropriately based on the context of the communication.

200 232 242 232 The WCAincludes both large language model (LLM) facilitiesand non-LLM facilities. The LLM facilitieshandle the interpretation of dynamically generated or non-predefined instructions from received messages. These facilities use large language models to translate human language inputs into structured tasks or actions, allowing for a flexible, context-aware response to communications directed at the user in any of their roles (e.g., as a tile lead or as a team member).

242 244 245 234 244 In contrast, the non-LLM facilitiesmanage predefined workflows and structured tasks. These include an executor, responsible for executing predefined scripts or other predefined sets of instructions, and an instruction interpreter, which converts incoming predefined instructions from the email and API systeminto executable scripts for the executor.

200 250 252 254 256 The WCAalso integrates several tools and monitoring components. The toolsinclude software such as flow tools(for task optimization and compilation), Electronic Design Automation (EDA) tools(used to manage chip design tiles), and machine learning (ML) models(which provide pattern analysis and/or other trained optimizations).

200 260 260 262 264 266 280 To ensure that tasks are executed properly, the WCAemploys a monitor, which oversees the performance of tasks and provides feedback. The monitorincludes a target analyzerto verify that tasks meet their performance targets, a quality-of-results (QOR) optimizer, and a status extractorto retrieve and summarize task status for the human user, regardless of their current role.

232 230 242 235 200 In the depicted embodiment, the LLM facilitiesare hosted on the local server, while the non-LLM facilitiesand tools are executed on the remote server. However, and as noted above, in various embodiments the WCAmay operate on a single server without such bifurcation.

200 200 130 175 200 280 120 160 280 1 FIG. 1 FIG. In operation, the WCAfacilitates communication and task management via email or other messages. Messages to workflow communications agents in the communications network, whether human-to-agent or agent-to-agent, are received by one or more workflow communications agents (e.g., WCA), each of which operates as a node in the agent communications network. Each workflow communications agent within the network is associated with a unique address. In examples described herein a workflow communications agent (such as AgentAor AgentBof, or WCA) is referenced by a specific real or virtual address that uniquely identifies the workflow communication agent. For example, in certain embodiments a WCA associated with a particular human usermay be identified as some combination of that user's identifier and its own tag (e.g., xxx@domain.com/agent_name). As shown inwith respect to user Haland user Robbie, agent tags (such as “AgentA” and “AgentB”) are unique among agents associated with a particular human user, but need not be unique in the overall network, as a message directed to Hal@domain.com/AgentA is routed differently than a message directed to Robbie@domain.com/AgentA.

200 232 242 280 234 In the depicted embodiment, the WCAutilizes a dual approach for task handling, in which LLM facilitieshandle non-predefined instructions and non-LLM facilitiesmanage predefined instructions. When human users (e.g., human user) send task instructions via message, these messages are periodically extracted by the email and API system, in which natural language instructions are parsed and recorded in one or more structured formats. As non-limiting examples, in various embodiments such instructions may be recorded in comma-separated values format (csv), plain text, Excel (.xls/.xlsx), JavaScript object notation (JSON), or other structured format.

200 232 242 The workflow communications agent (WCA) dynamically interprets and routes incoming messages based on their content, utilizing either the LLM facilitiesor non-LLM facilities, depending on the structure and complexity of the instructions provided.

234 242 232 When a message is received by the email and API system, the system first analyzes the message content to determine the nature of the instructions. Messages containing predefined keywords or structured instructions are routed to the non-LLM facilitiesfor immediate parsing and execution. On the other hand, unstructured, dynamic, or conversational messages that lack direct keywords are processed by the LLM facilities.

Instruction Script Run tile build run_tile_build.csh $project $tile $runDir $disk $params $tag Messages containing explicit, predefined instructions (e.g., “run tile build” or “restart flow”) are matched against a set of predefined keywords and task models. For instance, if the message contains the term “run build,” where one or both of “run” and “build” are defined keywords (segments of predefined content) it triggers a script that corresponds to a specific project or task associated with one or both of those keywords, such as:

245 244 200 Extract the command from the message content using keyword recognition. Map the extracted command to an existing script or predefined task model. Execute the script and report back the status to the human user via message. The instruction interpretertranslates these keywords into executable scripts, which are then carried out by the executor. For example, in an embodiment the WCAprocesses the instruction as follows:

Continuing the example, a message with a textual body such as “Run tile build for Project X” would directly trigger the run_tile_build.csh script, passing relevant parameters such as the project name and directory paths.

232 232 In various embodiments, messages that do not contain explicit keywords or that are phrased in a more conversational or ambiguous manner are routed to the LLM facilities. The LLM facilitiesinterpret the content, identifying the underlying task based on context and the user's communication patterns. For example, a message such as “Can you check the status of the latest tile build?” does not map directly to a predefined command but would be interpreted by the LLM as a request for a status report on a recent run.

232 Analyze the message using natural language processing to infer the task or request. Generate an appropriate response or action based on the inferred task. 242 Convert the inferred task into structured, executable instructions for the non-LLM facilitiesor return status information directly to the user. In this case, the LLM facilitieshandle the instruction as follows:

This process allows the WCA to handle a wide range of communication styles, ensuring that tasks are executed efficiently whether the instructions are explicit or implied. The flexibility of the LLM facilities means that even non-technical or vague requests can be processed and responded to appropriately.

242 232 244 252 254 260 Once the task is interpreted—either by keyword-based processing via non-LLM facilitiesor LLM-driven inference by the LLM facilities—it is passed to the executor, which carries out the task using the relevant tools such as flow toolsor EDA tools. Progress is then monitored by the monitor, which tracks performance and optimizes the execution where needed.

200 In certain embodiments, the WCAprovides task performance feedback to the human user, summarizing task progress, results, or any errors encountered during execution, whether the instruction was parsed by LLM or non-LLM components.

200 234 232 242 244 245 250 260 As will be appreciated, the WCAand one or more of its components (e.g., email and API system, LLM facilities, non-LLM facilities, executor, instruction interpreter, tools, and monitor) may, in various embodiments, be implemented as sets of instructions encoded and/or executed via one or more of hardware circuitry, firmware, or software instructions executed by one or more processors, as described in greater detail elsewhere herein.

3 FIG. 1 FIG. 200 illustrates an example workflow of the WCAfrom, including message parsing, task interpretation, and execution, according to some embodiments of the techniques described herein. The WCA processes incoming messages through its parsing and execution facilities, managing both predefined and dynamically generated instruction sets, and integrating tools and monitoring components to manage task-related content.

200 234 305 305 200 The WCAreceives a message, such as task-related content, via the email and API system. The content of this message is extracted and stored in tasks data, a .csv file that organizes message information into predefined columns such as sender, time, subject, and instructions. While in the present example the tasks dataand other data structures described herein utilize a . csv data structure, it will be appreciated that in various embodiments, other types of data and/or data structures may be utilized in accordance with the described techniques and example presented here. The WCAthen begins parsing the message to determine whether the content includes predefined segments.

245 305 315 325 335 In particular, the instruction interpreterprocesses the incoming message via tasks datato determine whether the task-related content contains predefined segments that map to existing instruction sets. During this process, the interpreter accesses various supporting data sources, which in the illustrated example include argument data(containing parameters or arguments associated with the predefined instructions; keyword data(including predefined keywords that trigger specific actions or predefined instruction sets; and instruction data(storing instructions for predefined tasks).

245 345 244 The instruction interpretercross-references the message content with these data sources to identify corresponding predefined instruction sets. Once identified, in the depicted example the instruction sets are stored in model data(tasksModel.csv), which is then used to direct the execution of tasks by the executor.

245 200 232 232 232 245 If the instruction interpreterdetermines that the task-related content does not contain predefined segments or keywords, the WCAtransfers the content to the LLM facilitiesfor further processing. The LLM facilitiesinterpret dynamic, unstructured instructions by analyzing the content for patterns or contexts that suggest an associated instruction set. The LLM facilitiesmay then generate new instruction sets or infer actions based on the task-related content, passing this information back to the instruction interpreterfor execution.

232 234 In certain embodiments, the LLM facilitiesare also responsible for summarizing the status of ongoing tasks and retrieving status updates, which are communicated back to the human user via the email and API system.

345 244 250 250 200 345 Once the model datais populated with instruction sets, the executorinitiates task execution, such as by programmatically interacting with various tools. In the depicted example, the toolsinclude EDA tools configured for design generation and optimization; flow tools configured for source code or design code compilation; and one or more tools configured for handling machine learning (ML) models, which may provide additional insights or optimizations during execution. It will be appreciated that in various configurations, embodiments and scenarios, a variety of domain-relevant tools may be programmatically instructed by the WCAbased on the model data.

200 250 200 260 The WCAensures that each tool receives the necessary parameters and instructions to carry out the assigned tasks, including adjusting execution parameters for execution of one or more predefined instruction sets. For example, in certain embodiments, execution parameters for one or more of the toolsmay be adjusted based on one or more performance metrics. In such embodiments, the WCAmay continuously monitor the status and performance of tasks via the monitor, which in the depicted example includes a target analyzer, responsible for ensuring that performance targets are met during task execution; a QOR optimizer, which adjusts task execution parameters to improve quality-of-results metrics; and a status extractor, which consolidates and retrieves information about the current status of task execution.

200 280 200 234 200 410 345 245 244 254 235 260 264 280 As one example of an operational workflow managed by a WCA (e.g., WCA), consider a physical design task related to timing analysis for a chip design. In this example, the human usersends a message to a destination address on the network (e.g., Hal1.chen@chip.com) containing task-related content, such as “Run timing analysis for Tile A on Project X,” to the WCA. Upon receiving this message via the email and API system, the WCAparses the task-related content to invoke the timing role of Agentand identify predefined keywords (“timing analysis,” “Tile A,” and “Project X”) and maps these keywords to corresponding instruction sets in the model data. The instruction interpreterconverts the keywords into an executable timing analysis script to effectuate those corresponding instruction sets, and assigns task parameters such as the project directory and tile identifier. The executorthen initiates the timing analysis script, interacting with relevant tools (e.g., EDA tools) hosted on the remote server. Progress and results of the analysis are monitored by the monitor, which tracks quality-of-results (QOR) metrics via the QOR optimizerand provides status updates to the human user.

200 280 200 232 232 252 245 244 260 262 280 234 As another example scenario, the WCAmay facilitate congestion analysis to address physical design challenges. In this scenario, the human usersubmits a message, “Analyze congestion for latest tile placement,” indicating a desire for the WCAto initiate a process in which the distribution of routing resources and the density of placed components (e.g., macros, standard cells) is evaluated with respect to a specific tile of the chip layout. Due to a lack of explicit predefined keywords in the submitted message, it is provided for parsing to the LLM facilities. The LLM facilitiesgenerate an appropriate instruction set by identifying the task's intent and mapping it to available tools, such as flow tools. The instruction interpretertranslates this generated instruction set into a script that is executable by the executor. The monitor(such as via target analyzer) verifies that the resulting analysis meets performance criteria and, in certain embodiments, may automatically adjust one or more execution parameters to optimize congestion mitigation strategies. Updates and results are communicated back to the human uservia the email and API system.

200 280 245 335 250 252 315 260 262 In a third example, the WCA coordinates the placement of macros during a chip design flow, adjusting the arrangement of large design blocks within one or more designated tiles of the relevant chip layout. A message, such as “Optimize macro placement for Tile B,” is received by the WCA, such as from a human useror from some other source (e.g., another WCA operating on the network). If predefined keywords (e.g., “macro placement,” “Tile B”) are detected, the instruction interpreterretrieves a corresponding script from instruction data. This script is executed using one or more of tools(such as flow tools) with parameters derived from the argument data. If any unexpected issues arise, such as macro-to-macro congestion, the monitoridentifies these via the target analyzerand, in certain embodiments, generates follow-up actions, such as re-running the optimization with adjusted parameters.

4 FIG. illustrates an example workflow of a distributed network of workflow communications agents, demonstrating how multiple WCA instances handle incoming task-related messages in a networked environment, according to some embodiments. Each WCA instance in the system may operate across different servers or environments, managing both predefined and dynamically generated instruction sets through large language models (LLMs) and non-LLM facilities. The depicted example also shows how messages are parsed and assigned to the appropriate WCA agents for execution.

234 450 445 460 In operation, a message containing task-related content is received via the email and API systemfrom a human user (e.g., the human user associated with address/identifier Hal1.chen@chip.com). The content of the message is extracted and organized into message dataand recorded into tasks data, which stores the extracted message details such as time, sender, and content. These tasks are parsed and analyzed by the interpreter.

460 200 In some embodiments, the interpreteris a component of the WCA. In such configurations, the interpreter processes the incoming messages and determines how to parse the content, identifying keywords or segments associated with predefined instructions. The interpreter directly interfaces with the WCA's instruction interpreter component to distribute tasks to the appropriate WCA instances for execution.

460 200 200 450 460 200 In other embodiments, the interpretermay be a third-party tool invoked by the WCAto handle the parsing process. In such cases, the WCAprogrammatically invokes and communicates with the external interpreter, such as providing it with the contents of message datafor analysis. The external interpreterprocesses the task-related content and returns results to the WCA, which then routes the tasks to the relevant workflow communications agents.

445 0 410 420 430 405 415 425 445 405 415 425 In certain embodiments, the tasks from tasks dataare assigned to different WCA agents based on the task content and system configuration. In the depicted example, three workflow communications agents—WCA agent, WCA agent1, and WCA agent2—are distributed across different servers. The system assigns tasks to the appropriate WCA based on predefined rules or dynamically generated criteria, with task assignments stored in assignment data files,, andfor each respective WCA. Thus, in the depicted example, the tasks dataserves as the central repository for organizing the extracted message details, while the assignment data files,,are used to track task assignments and ensure that each WCA agent receives the correct tasks based on the parsed message content.

Each WCA agent is responsible for executing its assigned tasks, and each instance is configured to run both LLM facilities and non-LLM facilities. These facilities are distributed across two operating systems (OS1 and OS2), as shown. In the depicted example, LLM facilities are operating under operating system OS1 and handle the interpretation of unstructured or dynamic task-related content, while non-LLM facilities operating under operating system OS2 manage predefined tasks and execution of structured instruction sets.

410 420 430 As shown, the system of workflow communications agents supports a multi-operating system environment, with each WCA running components across different servers or OS environments. As depicted, WCA agent0, WCA agent1, and WCA agent2all run LLM facilities on OS1 and non-LLM facilities on OS2. This division allows for flexible handling of both predefined and dynamically generated tasks, ensuring that the system can efficiently process different types of instructions based on the resources available in each operating environment. However, it will be appreciated that in various embodiments and scenarios, other combinations of operating systems, servers, and WCAs are implemented in accordance with techniques presented herein.

234 Once tasks are assigned to the appropriate WCA agents, each agent initiates execution of those tasks based on their respective instruction sets. Each WCA agent accesses tools and resources required to complete the task, including interaction with internal or external systems. The WCAs communicate status updates back to the human user or other agents within the network through the email and API system. In some cases, messages between agents may also be handled autonomously by the WCA instances, generating further instructions or triggering additional workflows.

5 FIG. 500 500 is a block diagram of a processing systemdesigned to implement one or more instances of workflow communications agents in accordance with one or more embodiments. The processing systemis generally designed to execute sets of instructions or commands to carry out tasks on behalf of an electronic device, such as a desktop computer, laptop computer, server, smartphone, tablet, game console, and the like. In various embodiments, this processing system may be distributed across multiple servers or environments, managing the execution of both predefined and dynamically generated instruction sets associated with one or more hosted WCAs.

500 505 500 510 500 505 500 5 FIG. The processing systemincludes or has access to a memoryor other storage component that is implemented using a non-transitory computer readable medium, such as dynamic random access memory (DRAM). The processing systemalso includes a busto support communication between entities implemented in the processing system, such as the memory. In certain embodiments, the processing systemincludes other buses, bridges, switches, routers, and the like, which are not shown inin the interest of clarity.

500 515 520 515 The processing systemincludes one or more parallel processorsthat are configured to render images for presentation on a display. In the context of a WCA-based system, the parallel processorsmay also handle tasks related to neural network processing, machine learning model inference, or data-driven optimization techniques as part of executing tasks managed by the WCA.

515 520 A parallel processor is a processor that is able to execute a single instruction on multiple data or threads in a parallel manner. Examples of parallel processors include graphics processing units (GPUs), massively parallel processors, single instruction multiple data (SIMD) architecture processors, and single instruction multiple thread (SIMT) architecture processors for performing graphics, machine intelligence, or compute operations. The parallel processorcan render objects to produce pixel values that are provided to the display. In some implementations, parallel processors are separate devices that are included as part of a computer. In other implementations such as advance processor units, parallel processors are included in a single device along with a host processor such as a central processor unit (CPU). Thus, although embodiments described herein may utilize a graphics processing unit (GPU) for illustration purposes, various embodiments and implementations are applicable to other types of parallel processors.

515 515 515 515 515 In certain embodiments, the parallel processoris also used for general-purpose computing. For instance, the parallel processorcan be used to implement machine learning algorithms such as one or more implementations of a neural network as described herein. The parallel processormay also process complex instructions related to LLM facilities or task optimization routines. In some cases, operations of multiple parallel processorsare coordinated to execute a machine learning algorithm, such as if a single parallel processordoes not possess enough processing power to run the machine learning algorithm on its own.

515 525 515 530 525 515 505 505 515 540 525 The parallel processorimplements multiple processing elements (also referred to as compute units)that are configured to execute instructions concurrently or in parallel. The parallel processoralso includes an internal (or on-chip) memorythat includes a local data store (LDS), as well as caches, registers, or buffers utilized by the compute units. The parallel processorcan execute instructions stored in the memoryand store information in the memorysuch as the results of the executed instructions. The parallel processoralso includes a command processorthat receives task requests and dispatches tasks to one or more of the compute units.

500 545 510 515 505 510 545 550 545 555 505 545 505 The processing systemalso includes a central processing unit (CPU)that is connected to the busand communicates with the parallel processorand the memoryvia the bus. The CPUimplements multiple processing elements (also referred to as processor cores)that are configured to execute instructions concurrently or in parallel. The CPUcan execute instructions such as program codestored in the memoryand the CPUcan store information in the memorysuch as the results of the executed instructions.

560 520 500 560 510 560 505 515 545 An input/output (I/O) enginehandles input or output operations associated with the display, as well as other elements of the processing systemsuch as keyboards, mice, printers, external disks, and the like. The I/O engineis coupled to the busso that the I/O enginecommunicates with the memory, the parallel processor, or the CPU.

545 515 500 515 525 525 540 525 In operation, the CPUissues commands to the parallel processoror other components of the systemto execute tasks related to instruction parsing, LLM operations, or dynamic task handling, and in some scenarios initiates processing of a kernel that represents the program instructions that are executed by the parallel processor. Multiple instances of the kernel, referred to herein as threads or work items, are executed concurrently or in parallel using subsets of the compute units. In some embodiments, the threads execute according to single-instruction-multiple-data (SIMD) protocols so that each thread executes the same instruction on different data. The threads are collected into workgroups (also termed thread groups) that are executed on different compute units. For example, the command processorcan receive these commands and schedule tasks for execution on the compute units.

515 515 In some embodiments, the parallel processorimplements a graphics pipeline that includes multiple stages configured for concurrent processing of different primitives in response to a draw call. Stages of the graphics pipeline in the parallel processorcan concurrently process different primitives generated by an application, such as a video game. When geometry is submitted to the graphics pipeline, hardware state settings are chosen to define a state of the graphics pipeline. Examples of state include rasterizer state, a blend state, a depth stencil state, a primitive topology type of the submitted geometry, and the shaders (e.g., vertex shader, domain shader, geometry shader, hull shader, pixel shader, and the like) that are used to render the scene.

500 500 515 As used herein, a layer in a neural network is a hardware-or software-implemented construct in a processing system, such as processing system. In various embodiments, such a layer may perform one or more operations via processing circuitry of the processing systemto serve as a collection or group of interconnected neurons or nodes, arranged in a structure that can be optimized for execution on one or more parallel processors (e.g., parallel processors) or other similar computation units. Such computation units can, in certain embodiments, comprise one or more graphics processing units (GPUs), massively parallel processors, single instruction multiple data (SIMD) architecture processors, and single instruction multiple thread (SIMT) architecture processors.

505 545 515 Each layer processes and transforms input data—for example, raw data input into an input layer or the transformed data passed between hidden layers. This transformation process involves the use of an output weight matrix, which is held in memory (e.g., memory) and manipulated by the central processing unit (CPU)and/or the parallel processors.

525 515 In some instances, such layers may be distributed across multiple processing units within a system. For instance, different layers or groups of layers may be executed on different compute unitswithin a single parallel processor, or even across multiple parallel processors if warranted by system architecture and the complexity of the neural network.

The output of each layer, after processing and transformation, serves as input for the subsequent layer. In the case of the final output layer, it produces the results or predictions of the neural network. In various embodiments, such results can be utilized by the system or fed back into the network as part of a training or fine-tuning process. In some embodiments, the training or fine-tuning process involves adjusting one or more weights in the output weight matrix associated with each layer to improve performance of the neural network.

6 FIG. 600 200 illustrates an operational flow diagram of a routinefor processing task-related content via a workflow communications agent (WCA) in accordance with one or more embodiments. The operational flow diagram illustrates how the WCA processes task-related messages, determines if predefined instruction sets apply, and generates new instruction sets if necessary.

605 234 The routine begins at block, in which the WCA receives a message including task-related content. This message can be received from a human user or another agent within the system, such as via the email and API system, as described elsewhere herein. For example, the message may contain one or more instructions or requests related to a task.

610 640 At decision block, the WCA determines whether the task-related content includes one or more segments of predefined content, such as known instructions or keywords that have been associated with existing instruction sets (e.g., scripts) in the system. If the message contains any such segments of predefined content, the routine proceeds to block, in which the WCA initiates execution of one or more predefined instruction sets based on the task-related content.

615 If the task-related content does not include predefined content, the routine proceeds to block, where the WCA provides the task-related content to one or more large language models (LLMs). The LLMs are responsible for interpreting dynamic, unstructured content and determining whether it is associated with an existing instruction set. The LLM analyzes the message to infer any task instructions from the unstructured content.

620 640 625 At decision block, the WCA checks if the LLM has determined that the task-related content is associated with one or more defined instruction sets. If so, the routine moves to blockto initiate the execution of the associated instruction set(s). If not, the routine proceeds to decision block, where the WCA determines whether to generate new instruction sets based on the task-related content. In this manner, even if the message contains new or previously unseen content, the WCA can still generate an appropriate instruction set for execution.

630 635 If the WCA determines that it cannot generate an instruction set based on the task-related content, the routine proceeds to blockand terminates. If, however, the WCA determines that it can generate an instruction set, the routine proceeds to block, where the WCA generates one or more defined instruction sets based on the unstructured task-related content. These newly generated instruction sets may be based on the LLM's interpretation of the content or other logic embedded within the WCA.

640 610 620 635 At block, the WCA initiates execution of the defined instruction set(s), whether they were predefined (and identified in one of blocksand) or newly generated (at block). In various embodiments and scenarios, the execution of these instruction sets can involve programmatically interacting with one or more tools to perform one or more task actions.

1 6 FIGS.- In some embodiments, the apparatus and techniques described above are implemented in a system including one or more integrated circuit (IC) devices (also referred to as integrated circuit packages or microchips), such as the workflow communications agent(s) described above with reference to. Electronic design automation (EDA) and computer aided design (CAD) software tools may be used in the design and fabrication of these IC devices. These design tools typically are represented as one or more software programs. The one or more software programs include code executable by a computer system to manipulate the computer system to operate on code representative of circuitry of one or more IC devices so as to perform at least a portion of a process to design or adapt a manufacturing system to fabricate the circuitry. This code can include instructions, data, or a combination of instructions and data. The software instructions representing a design tool or fabrication tool typically are stored in a computer readable storage medium accessible to the computing system. Likewise, the code representative of one or more phases of the design or fabrication of an IC device may be stored in and accessed from the same computer readable storage medium or a different computer readable storage medium.

A computer readable storage medium may include any non-transitory storage medium, or combination of non-transitory storage media, accessible by a computer system during use to provide instructions and/or data to the computer system. Such storage media can include, but is not limited to, optical media (e.g., compact disc (CD), digital versatile disc (DVD), Blu-Ray disc), magnetic media (e.g., floppy disc, magnetic tape, or magnetic hard drive), volatile memory (e.g., random access memory (RAM) or cache), non-volatile memory (e.g., read-only memory (ROM) or Flash memory), or microelectromechanical systems (MEMS)-based storage media. The computer readable storage medium may be embedded in the computing system (e.g., system RAM or ROM), fixedly attached to the computing system (e.g., a magnetic hard drive), removably attached to the computing system (e.g., an optical disc or Universal Serial Bus (USB)-based Flash memory), or coupled to the computer system via a wired or wireless network (e.g., network accessible storage (NAS)).

One or more of the elements described above is circuitry designed and configured to perform the corresponding operations described above. Such circuitry, in at least some embodiments, is any one of, or a combination of, a hardcoded circuit (e.g., a corresponding portion of an application specific integrated circuit (ASIC) or a set of logic gates, storage elements, and other components selected and arranged to execute the ascribed operations), a programmable circuit (e.g., a corresponding portion of a field programmable gate array (FPGA) or programmable logic device (PLD)), or one or more processors executing software instructions that cause the one or more processors to implement the ascribed actions. In some embodiments, the circuitry for a particular element is selected, arranged, and configured by one or more computer-implemented design tools. For example, in some embodiments the sequence of operations for a particular element is defined in a specified computer language, such as a register transfer language, and a computer-implemented design tool selects, configures, and arranges the circuitry based on the defined sequence of operations.

Within this disclosure, in some cases, different entities (which are variously referred to as “components,” “units,” “devices,” “circuitry,” etc.) are described or claimed as “configured” to perform one or more tasks or operations. This formulation—[entity] configured to [perform one or more tasks]—is used herein to refer to physical structure (e.g., electronic circuitry). More specifically, this formulation is used to indicate that this physical structure is arranged to perform the one or more tasks during operation. Such physical structure can be said to be “configured to” perform some task even if the structure is not currently being operated. A “memory device configured to store data” is intended to cover, for example, an integrated circuit that has circuitry that stores data during operation, even if the integrated circuit in question is not currently being used (e.g., a power supply is not connected to it). Thus, an entity described or recited as “configured to” perform some task refers to something physical, such as a device, circuitry, memory storing program instructions executable to implement the task, etc. This phrase is not used herein to refer to something intangible. Further, the term “configured to” is not intended to mean “configurable to.” An unprogrammed field programmable gate array, for example, would not be considered to be “configured to” perform some specific function, although it could be “configurable to” perform that function after programming. Additionally, reciting in the appended claims that a structure is “configured to” perform one or more tasks is expressly intended not to be interpreted as having means-plus-function elements.

In some embodiments, certain aspects of the techniques described above may implemented by one or more processors of a processing system executing software. The software includes one or more sets of executable instructions stored or otherwise tangibly embodied on a non-transitory computer readable storage medium. The software can include the instructions and certain data that, when executed by the one or more processors, manipulate the one or more processors to perform one or more aspects of the techniques described above. The non-transitory computer readable storage medium can include, for example, a magnetic or optical disk storage device, solid state storage devices such as Flash memory, a cache, random access memory (RAM) or other non-volatile memory device or devices, and the like. The executable instructions stored on the non-transitory computer readable storage medium may be in source code, assembly language code, object code, or other instruction format that is interpreted or otherwise executable by one or more processors.

Note that not all of the activities or elements described above in the general description are required, that a portion of a specific activity or device may not be required, and that one or more further activities may be performed, or elements included, in addition to those described. Still further, the order in which activities are listed are not necessarily the order in which they are performed. Also, the concepts have been described with reference to specific embodiments. However, one of ordinary skill in the art appreciates that various modifications and changes can be made without departing from the scope of the present disclosure as set forth in the claims below. Accordingly, the specification and figures are to be regarded in an illustrative rather than a restrictive sense, and all such modifications are intended to be included within the scope of the present disclosure.

Benefits, other advantages, and solutions to problems have been described above with regard to specific embodiments. However, the benefits, advantages, solutions to problems, and any feature(s) that may cause any benefit, advantage, or solution to occur or become more pronounced are not to be construed as a critical, required, or essential feature of any or all the claims. Moreover, the particular embodiments disclosed above are illustrative only, as the disclosed subject matter may be modified and practiced in different but equivalent manners apparent to those skilled in the art having the benefit of the teachings herein. No limitations are intended to the details of construction or design herein shown, other than as described in the claims below. It is therefore evident that the particular embodiments disclosed above may be altered or modified and all such variations are considered within the scope of the disclosed subject matter. Accordingly, the protection sought herein is as set forth in the claims below.